Real-time Video Face Cartoon Generation Method Based on Facial Feature Points
A face feature and real-time video technology, applied in the fields of image processing and computer vision, can solve problems such as inconsistent expression changes, data errors, and easy drift, etc., to meet real-time requirements, simple operating environment requirements, and good results
Active Publication Date: 2017-12-15
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF3 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The existing optical flow method is not very accurate in tracking feature points and is very sensitive to illumination. Especially when the texture near the feature points is complex, it is easy to drift, which makes the data of facial expression changes wrong, resulting in cartoon faces. Changes do not match expression changes on real faces
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0022] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the implementation methods and accompanying drawings.
[0023] see figure 1 , the real-time video face cartoon generation method based on facial feature points of the present invention comprises the following steps:
[0024] Step 1: Turn on the video capture device, such as turning on the video or camera;
[0025] Step 2: Pause the video frame, intercept a frame of positive neutral expression image from the input video, and define this video frame as the reference frame. In order to better support subsequent processing, the face of the intercepted positive neutral expression image should preferably be unoccluded.
[0026] Step 3: Automatically crop the captured image to obtain a face image suitable for processing and perform cartoonization to obtain a cartoon face C with a certain artistic...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a real-time video face cartoon generation method based on face feature points. The present invention firstly selects a frame of positive neutral expression image from the input video as a reference frame, carries out face cartoonization processing to the reference frame and saves the cartoon eyes, cartoon eyebrows, cartoon nose and the cartoon facial contour including the facial contour of the reference frame ; Based on the face feature points of the video frame, the face variation of the reference frame and the video frame is extracted and normalized, and the input video frame whose face variation of the reference frame and the reference frame meets the change threshold is used as the starting point of the cartoon video The initial frame; based on the cartoon image of the reference frame, a video cartoon is generated for the initial frame and subsequent frames of the initial frame. The invention is used for the face cartoon generation of real-time video, and has the beneficial effects that the generated cartoon video has better effect, meets the real-time requirements of the video, and has simple requirements on the operating environment.
Description
technical field [0001] The invention belongs to the technical field of image processing and computer vision, and specifically relates to a method for processing real-time input camera video information to generate corresponding cartoon animation. Background technique [0002] At present, the methods for generating video face cartoon animation mainly include methods based on video streams, methods based on material reuse, physical model methods, and behavior-driven methods. [0003] Methods based on video streams can be divided into: direct cartoon rendering, video information extraction rendering, and expression-driven rendering. Direct cartoon drawing is to sequentially process the content of the video stream through image processing to obtain a sequence of cartoon pictures of a certain artistic style. This method does not utilize the very related information between video frames and has a large degree of redundancy. The processing time of a single image has very high requ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T3/00
CPCG06T3/18
Inventor 李宏亮李君涵马金秀杨德培侯兴怀罗雯怡姚梦琳
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA